Doctoral Thesis Oral Defense - Christopher Canel
July 17, 2026 11:00AM—1:00PM
Location:
4405
-
Gates and Hillman Centers
Speaker:
CHRISTOPHER CANEL,
Ph.D. Candidate, Computer Science Department, Carnegie Mellon University
https://www.ccanel.com/
Current techniques for rate control in computer networks are not aligned with the policies and considerations of both endpoints in a connection. Historically, fine-grained rate control has been the sender's responsibility through the Transmission Control Protocol (TCP) and its congestion control algorithm (CCA). However, the receiver, either due to conflicting priorities or greater visibility into congestion, would often be better served by a different rate allocation than the sender. A simple example is a many-flow incast in a datacenter network: each sender independently seeks to transmit as quickly as possible, while the receiver can observe that each flow should converge to a small fraction of the last-hop link rate. Likewise, on the Internet, each service attempts to maximize its own throughput, whereas a user may desire fairness across services.
To bridge the gap between endpoint objectives, we argue for a dual-endpoint approach to congestion control that incorporates the receiver into the rate decision as well. Specifically, we advocate for receiver-assisted congestion control, where the receiver provides lightweight hints to senders about the rate regime in which they should operate. Receiver-assisted congestion control differs from fully receiver-based techniques because the sender maintains control over the packet stream, and our proposal offers capabilities similar to in-network rate control with fewer practical challenges. To implement receiver assistance, we revisit the well-known technique of TCP flow control and show it to be a powerful primitive to enable expressive receiver policies that does not require modifications to TCP, the sender's CCA, or applications.
This thesis explores two environments with differing endpoint objectives to show that receiver-assisted congestion control gives both endpoints a stake in bandwidth allocation decisions. First, we consider datacenter incast bursts, where the receiver’s observability into the traffic pattern enables dual-endpoint control to schedule hundreds or thousands flows into a healthy regime that both improves network utilization and reduces receiver packet processing overheads. Second, we turn to the Internet at large and show the expressivity of dual-endpoint control by resolving common challenges that arise due to conflicting receiver policies regarding rate control granularity, algorithm, and optimization metric.
Thesis Committee:
Srinivasan Seshan (Chair)
Justine Sherry
Peter Steenkiste
Neil Spring (Meta)
Contact
Matt Stewart